Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers

TL;DR

This paper presents a new computational approach for detecting adverbial presupposition triggers like 'also' and 'again', which is useful for natural language generation tasks, using novel datasets and an efficient attention mechanism.

Contribution

The paper introduces the first computational method for identifying adverbial presupposition triggers, with new datasets and a lightweight attention mechanism that improves detection performance.

Findings

Model outperforms baseline methods including LSTM language models.

New datasets derived from Penn Treebank and Gigaword.

Attention mechanism enhances detection without extra trainable parameters.

Abstract

We introduce the task of predicting adverbial presupposition triggers such as also and again. Solving such a task requires detecting recurring or similar events in the discourse context, and has applications in natural language generation tasks such as summarization and dialogue systems. We create two new datasets for the task, derived from the Penn Treebank and the Annotated English Gigaword corpora, as well as a novel attention mechanism tailored to this task. Our attention mechanism augments a baseline recurrent neural network without the need for additional trainable parameters, minimizing the added computational cost of our mechanism. We demonstrate that our model statistically outperforms a number of baselines, including an LSTM-based language model.